Metacognitive Reasoning in Energy Based Models using Instance Based Learning Theory

Researchers introduced MERITED, a framework for metacognitive reasoning that combines Instance-Based Learning Theory (IBLT) with Energy Based Models (EBMs) to let AI systems allocate computational effort based on uncertainty before producing an output. The work, published as arXiv:2610.00399v1, includes two contributions: the training and open weight sharing of a 191M parameter reasoning EBM, and an implementation of the MERITED framework for dynamic compute allocation using an IBL model. The authors position the approach as addressing a limitation of Large Language Models, which cannot estimate uncertainty about an output without first responding or dynamically allocate resources to producing an output.

arXiv:2610.00399v1 Announce Type: new Abstract: Metacognition involves reasoning about cognitive processes themselves. An example is in resource allocation where we choose how much time and effort to put into a reasoning task before we begin based on our confidence. Current Artificial Intelligence AI systems that rely on Large Language Models LLMs cannot estimate their uncertainty about an output without first responding, and cannot dynamically allocate resources to producing an output, making this type of metacognitive process difficult. A recently proposed alternative to classic transformer architectures that addresses these two concerns is the Energy Based Model EBM which allows for interpretable uncertainty modeling and dynamic allocation of compute resources. While EBMs can allow for control of these two processes, the actual metacognitive task of determining compute allocation based on uncertainty is not directly addressed. Instance-Based Learning Theory IBLT provides an approach to modeling human-like decisions from experience that has previously been applied to predicting human metacognitive reasoning. In this paper we introduce a framework for MEtacognitive Reasoning with Instance-based Learning Theory and Energy Dynamics MERITED . Grounded in IBLT, this framework allows for control of the computational effort allocated in an EBM to allow for metacognitive control over reasoning effort based on uncertainty while remaining computationally efficient. This work has two main contributions, the training and open weight sharing of a 191M parameter reasoning EBM, and an implementation of the MERITED framework for dynamic compute allocation using an IBL model.